Text Generation
cortiq
English
Russian
Chinese
cmf
quantized
q4tp
Mixture of Experts
code
expert-pruning
speculative-decoding
vulkan
cuda
Instructions to use infosave/Qwen3.8-Flash-Next-Fast-Code-cmf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- cortiq
How to use infosave/Qwen3.8-Flash-Next-Fast-Code-cmf with cortiq:
# one Rust binary, no additional dependencies cargo install cortiq-cli # or a prebuilt binary from github.com/infosave2007/cmf/releases hf download infosave/Qwen3.8-Flash-Next-Fast-Code-cmf --include "*.cmf" --local-dir . ls *.cmf # some repos ship more than one quantization
cortiq run FILE.cmf --prompt "What is the capital of France?"
cortiq serve FILE.cmf --port 8080 # OpenAI-compatible server
- Notebooks
- Google Colab
- Kaggle
Card: plain Chinese troubleshooting line
Browse files
README.md
CHANGED
|
@@ -419,7 +419,7 @@ CMF_QWEN_PROFILE=fast-code.profile cortiq run qwen38-flash-next-fast-code.cmf --
|
|
| 419 |
|
| 420 |
### 常见问题
|
| 421 |
|
| 422 |
-
-
|
| 423 |
`lib64` 加入 `LD_LIBRARY_PATH`。之后日志中会出现 `qwen4 cuda: arena prefilled with …`。
|
| 424 |
- **显存不足**:关闭其他使用 GPU 的程序,或把 `CMF_GPU_VRAM_MB` 设小一些。
|
| 425 |
- **内存不足 64 GB**:去掉 `CMF_QWEN_CUDA_REG_ALL=1`(必要时也去掉 `CMF_QWEN_CUDA_REG=1`),速度会变慢。
|
|
|
|
| 419 |
|
| 420 |
### 常见问题
|
| 421 |
|
| 422 |
+
- 日志出现 `libnvrtc (CUDA toolkit) was not found` 或 `qwen4 cuda: …; staying on the host path`:安装 CUDA 12.8+,并把其
|
| 423 |
`lib64` 加入 `LD_LIBRARY_PATH`。之后日志中会出现 `qwen4 cuda: arena prefilled with …`。
|
| 424 |
- **显存不足**:关闭其他使用 GPU 的程序,或把 `CMF_GPU_VRAM_MB` 设小一些。
|
| 425 |
- **内存不足 64 GB**:去掉 `CMF_QWEN_CUDA_REG_ALL=1`(必要时也去掉 `CMF_QWEN_CUDA_REG=1`),速度会变慢。
|